{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7RJ4CSGDFEDTCUSQQQ6AXIAJRH","short_pith_number":"pith:7RJ4CSGD","schema_version":"1.0","canonical_sha256":"fc53c148c32907315250843c0ba00989e9bf1e24547156fc95670c652bd6c016","source":{"kind":"arxiv","id":"2505.18549","version":1},"attestation_state":"computed","paper":{"title":"MSA at BEA 2025 Shared Task: Disagreement-Aware Instruction Tuning for Multi-Dimensional Evaluation of LLMs as Math Tutors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ali Hamdi, Baraa Hikal, Islam Oshallah, Mohamed Basem","submitted_at":"2025-05-24T06:32:02Z","abstract_excerpt":"We present MSA-MathEval, our submission to the BEA 2025 Shared Task on evaluating AI tutor responses across four instructional dimensions: Mistake Identification, Mistake Location, Providing Guidance, and Actionability. Our approach uses a unified training pipeline to fine-tune a single instruction-tuned language model across all tracks, without any task-specific architectural changes. To improve prediction reliability, we introduce a disagreement-aware ensemble inference strategy that enhances coverage of minority labels. Our system achieves strong performance across all tracks, ranking 1st i"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.18549","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T06:32:02Z","cross_cats_sorted":[],"title_canon_sha256":"d1f7e09ae32b28584f4873b48f508405d049c0cc9e41c18cc3fd580beddf192d","abstract_canon_sha256":"1e77bc6c1854a3606f7207fb82eccbf3d64379dc8c7582afb7a16cdef18617d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:48.264874Z","signature_b64":"YL2gVX9nA0vw7v8zOepdKsaxDBCyVcrZ4mt9jfR7TXXie87UtscPmjlR0aloB2Gkb+f23dl8sR1gznHVj8HlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc53c148c32907315250843c0ba00989e9bf1e24547156fc95670c652bd6c016","last_reissued_at":"2026-07-05T11:08:48.264386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:48.264386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MSA at BEA 2025 Shared Task: Disagreement-Aware Instruction Tuning for Multi-Dimensional Evaluation of LLMs as Math Tutors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ali Hamdi, Baraa Hikal, Islam Oshallah, Mohamed Basem","submitted_at":"2025-05-24T06:32:02Z","abstract_excerpt":"We present MSA-MathEval, our submission to the BEA 2025 Shared Task on evaluating AI tutor responses across four instructional dimensions: Mistake Identification, Mistake Location, Providing Guidance, and Actionability. Our approach uses a unified training pipeline to fine-tune a single instruction-tuned language model across all tracks, without any task-specific architectural changes. To improve prediction reliability, we introduce a disagreement-aware ensemble inference strategy that enhances coverage of minority labels. Our system achieves strong performance across all tracks, ranking 1st i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18549","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.18549/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.18549","created_at":"2026-07-05T11:08:48.264451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18549v1","created_at":"2026-07-05T11:08:48.264451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18549","created_at":"2026-07-05T11:08:48.264451+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RJ4CSGDFEDT","created_at":"2026-07-05T11:08:48.264451+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RJ4CSGDFEDTCUSQ","created_at":"2026-07-05T11:08:48.264451+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RJ4CSGD","created_at":"2026-07-05T11:08:48.264451+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7RJ4CSGDFEDTCUSQQQ6AXIAJRH","json":"https://pith.science/pith/7RJ4CSGDFEDTCUSQQQ6AXIAJRH.json","graph_json":"https://pith.science/api/pith-number/7RJ4CSGDFEDTCUSQQQ6AXIAJRH/graph.json","events_json":"https://pith.science/api/pith-number/7RJ4CSGDFEDTCUSQQQ6AXIAJRH/events.json","paper":"https://pith.science/paper/7RJ4CSGD"},"agent_actions":{"view_html":"https://pith.science/pith/7RJ4CSGDFEDTCUSQQQ6AXIAJRH","download_json":"https://pith.science/pith/7RJ4CSGDFEDTCUSQQQ6AXIAJRH.json","view_paper":"https://pith.science/paper/7RJ4CSGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18549&json=true","fetch_graph":"https://pith.science/api/pith-number/7RJ4CSGDFEDTCUSQQQ6AXIAJRH/graph.json","fetch_events":"https://pith.science/api/pith-number/7RJ4CSGDFEDTCUSQQQ6AXIAJRH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RJ4CSGDFEDTCUSQQQ6AXIAJRH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RJ4CSGDFEDTCUSQQQ6AXIAJRH/action/storage_attestation","attest_author":"https://pith.science/pith/7RJ4CSGDFEDTCUSQQQ6AXIAJRH/action/author_attestation","sign_citation":"https://pith.science/pith/7RJ4CSGDFEDTCUSQQQ6AXIAJRH/action/citation_signature","submit_replication":"https://pith.science/pith/7RJ4CSGDFEDTCUSQQQ6AXIAJRH/action/replication_record"}},"created_at":"2026-07-05T11:08:48.264451+00:00","updated_at":"2026-07-05T11:08:48.264451+00:00"}